mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-04-25 08:26:21 +02:00
125 lines
4.1 KiB
YAML
125 lines
4.1 KiB
YAML
post:
|
|
tags:
|
|
- Flow Services
|
|
summary: Text completion - direct LLM generation
|
|
description: |
|
|
Direct text completion using LLM without retrieval augmentation.
|
|
|
|
## Text Completion Overview
|
|
|
|
Pure LLM generation for:
|
|
- General knowledge questions
|
|
- Creative writing
|
|
- Code generation
|
|
- Analysis and reasoning
|
|
- Any task not requiring specific document/graph context
|
|
|
|
## System vs Prompt
|
|
|
|
- **system**: Sets LLM behavior, role, constraints
|
|
- "You are a helpful assistant"
|
|
- "You are an expert Python developer"
|
|
- "Respond in JSON format"
|
|
- **prompt**: The actual user request/question
|
|
|
|
## Streaming
|
|
|
|
Enable `streaming: true` to receive tokens as generated:
|
|
- Multiple messages with partial `response`
|
|
- Final message with `end-of-stream: true`
|
|
|
|
Without streaming, returns complete response in single message.
|
|
|
|
## Token Counting
|
|
|
|
Response includes token usage:
|
|
- `in-token`: Input tokens (system + prompt)
|
|
- `out-token`: Generated tokens
|
|
- Useful for cost tracking and optimization
|
|
|
|
## When to Use
|
|
|
|
Use text-completion when:
|
|
- No specific context needed (general knowledge)
|
|
- System prompt provides sufficient context
|
|
- Want direct control over prompting
|
|
|
|
Use document-rag/graph-rag when:
|
|
- Need to ground response in specific documents
|
|
- Want to leverage knowledge graph relationships
|
|
- Require citations or provenance
|
|
|
|
operationId: textCompletionService
|
|
security:
|
|
- bearerAuth: []
|
|
parameters:
|
|
- name: flow
|
|
in: path
|
|
required: true
|
|
schema:
|
|
type: string
|
|
description: Flow instance ID
|
|
example: my-flow
|
|
requestBody:
|
|
required: true
|
|
content:
|
|
application/json:
|
|
schema:
|
|
$ref: '../../components/schemas/text-completion/TextCompletionRequest.yaml'
|
|
examples:
|
|
basicCompletion:
|
|
summary: Basic text completion
|
|
value:
|
|
system: You are a helpful assistant that provides concise answers.
|
|
prompt: Explain the concept of recursion in programming.
|
|
codeGeneration:
|
|
summary: Code generation with streaming
|
|
value:
|
|
system: You are an expert Python developer. Provide clean, well-documented code.
|
|
prompt: Write a function to calculate the Fibonacci sequence using memoization.
|
|
streaming: true
|
|
jsonResponse:
|
|
summary: Structured output request
|
|
value:
|
|
system: You are a JSON API. Respond only with valid JSON, no other text.
|
|
prompt: |
|
|
Extract key information from this text and return as JSON with fields:
|
|
title, author, year, summary.
|
|
|
|
Text: "The Theory of Everything by Stephen Hawking (2006) explores..."
|
|
responses:
|
|
'200':
|
|
description: Successful response
|
|
content:
|
|
application/json:
|
|
schema:
|
|
$ref: '../../components/schemas/text-completion/TextCompletionResponse.yaml'
|
|
examples:
|
|
completeResponse:
|
|
summary: Complete non-streaming response
|
|
value:
|
|
response: |
|
|
Recursion is a programming technique where a function calls itself
|
|
to solve a problem by breaking it down into smaller, similar subproblems.
|
|
Each recursive call works on a simpler version until reaching a base case.
|
|
in-token: 45
|
|
out-token: 128
|
|
model: gpt-4
|
|
end-of-stream: false
|
|
streamingChunk:
|
|
summary: Streaming response chunk
|
|
value:
|
|
response: "Recursion is a programming technique"
|
|
end-of-stream: false
|
|
streamingComplete:
|
|
summary: Streaming complete with tokens
|
|
value:
|
|
response: ""
|
|
in-token: 45
|
|
out-token: 128
|
|
model: gpt-4
|
|
end-of-stream: true
|
|
'401':
|
|
$ref: '../../components/responses/Unauthorized.yaml'
|
|
'500':
|
|
$ref: '../../components/responses/Error.yaml'
|